A Movable Waste Classification System Based on Human-Computer Interaction Technology

Yuyan Zhu

doi:10.47297/taposatWSP2633-456930.20260705

PDF
Export
Share
Collection
Album

A Movable Waste Classification System Based on Human-Computer Interaction Technology

Volume 7, Issue 5

Views: 0 Downloads: 0

A Movable Waste Classification System Based on Human-Computer Interaction Technology
A Movable Waste Classification System Based on Human-Computer Interaction Technology
School of Information and Communication Engineering, Dalian Nationalities University, Dalian, Liaoning, 116600, China
Vol. 7, Issue 5, Pages: 152-158(2026)
Online First：15 July 2026，

Published：30 May 2026
DOI：10.47297/taposatWSP2633-456930.20260705
Accepted：

Scan QR Code

Zhu Yuyan.A Movable Waste Classification System Based on Human-Computer Interaction Technology[J].Theory and Practice of Science and Technology,2026,07(05):152-158.
DOI：

Zhu Yuyan.A Movable Waste Classification System Based on Human-Computer Interaction Technology[J].Theory and Practice of Science and Technology,2026,07(05):152-158. DOI： 10.47297/taposatWSP2633-456930.20260705.

摘要

Abstract

This paper presents a movable waste classification system based on human-computer interaction technology. The system employs an STM32 microcontroller as the core control unit

integrated with an OV7725 camera and a MobileViT lightweight visual model for real-time waste identification. A dual-channel data fusion architecture combining pre-labeled reference data with dynamically captured images enhances recognition accuracy. The hardware includes a Mecanum-wheeled mobile chassis for omnidirectional movement and servo-controlled mechanisms for precise waste sorting. Multimodal interaction is achieved through an adaptive touchscreen

multi-dialect voice recognition

and a remote mobile application. An IoT-based platform with edge-cloud collaboration enables real-time monitoring and operational alerts. Experimental results demonstrate robust performance in classification accuracy and environmental adaptability. Key innovations include the dual-channel data fusion approach

integrated multimodal interaction

and networked intelligent management. This system offers significant improvements in automation efficiency and user engagement compared to conventional manual sorting methods.Compared with conventional manual sorting methods

this system offers substantial improvements in both automation efficiency and user engagement.

关键词

Keywords

references

Mittal G, Yagnik KB, Garg M, et al. SpotGarbage: smartphone app to detect garbage using deep learning [C] // Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, 2016: 940-945.

ADEDEJI O, WANG Z. Intelligent waste classification system using deep learning convolutional neural network [J]. Procedia Manuf, 2019, 35: 607-612.

WEI S F, CHENG Z L. Automatic garbage detection of urban scenes based on images[J]. Integration Technology, 2017, 6(01): 39-52.

YE H Y, GUO L D, LI Y X, et al. Design of intelligent domestic garbage classification system based on improved YOLOv5 algorithm[J]. Environmental Engineering, 2025, 43(04): 232-241.

YU X P. Road garbage detection from fixed perspective based on convolutional neural network[D]. Wuhan: Huazhong University of Science and Technology, 2019.

CAI H C. Research on garbage classification and recognition system based on computer vision[D]. Wuhan: Wuhan Institute of Technology, 2022.

JIA Q, WANG M L, LIU S Q, ZHU G. Review on omnidirectional mobile robots[J]. Manufacturing Automation, 2015, 37(7): 131-134.

Saenz A, Santibañez V, Bugarin E, Dzul A, Ríos H, Villalobos-Chin J. Velocity control of an omnidirectional wheeled mobile robot using computed voltage control with visual feedback: Experimental results[J]. International Journal of Control, Automation and Systems, 2021, 19(9): 1089-1102.

MEHTA S,RASTEGARI M.MobileViT:Light-weight,general-purpose,and mobile-friendly vision transformer[J/OL ] .arXiv: 2110.02178 ,2021.

Alert me when the article has been cited

Submit

A Review of Human-Machine Interaction Methods for Consumer Drones in the Context of the Low-Altitude Economy

Research on Obstacle Avoidance for UAV Patrol Based on Vision

Toward Intelligent Virtual Anchor: Generative AI for Unified Multimodal Generation

Design optimization of rehabilitation equipment based on ergonomics

Digital Protection and Display of Cantonese Embroidery Patterns Based on CAD and Human-computer Interaction

Related Author

Jiayuan Sun School of Intelligent Manufacturing and Smart Transportation, Suzhou City University

Jiamin Zhao Jiangning Campus, School of International Education, Jinling Institute of Technology

Xinyu Zhong Department of Electronics, University of Liverpool, Liverpool L69, United Kingdom

Li Li Geely University of China

Xiaoli Qi

Hongming Li

Related Institution

School of Intelligent Manufacturing and Smart Transportation, Suzhou City University

Jiangning Campus, School of International Education, Jinling Institute of Technology

Department of Electronics, University of Liverpool, Liverpool L69, United Kingdom

Geely University of China

Dongguan Polytechnic

⁰